arXiv Open Access 2025

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

AgiBot-World-Contributors Qingwen Bu Jisong Cai Li Chen Xiuqi Cui +47 lainnya
Lihat Sumber

Abstrak

We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence.

Topik & Kata Kunci

Penulis (52)

AgiBot-World-Contributors

Q

Qingwen Bu

J

Jisong Cai

L

Li Chen

X

Xiuqi Cui

Y

Yan Ding

S

Siyuan Feng

S

Shenyuan Gao

X

Xindong He

X

Xuan Hu

X

Xu Huang

S

Shu Jiang

Y

Yuxin Jiang

C

Cheng Jing

H

Hongyang Li

J

Jialu Li

C

Chiming Liu

Y

Yi Liu

Y

Yuxiang Lu

J

Jianlan Luo

P

Ping Luo

Y

Yao Mu

Y

Yuehan Niu

Y

Yixuan Pan

J

Jiangmiao Pang

Y

Yu Qiao

G

Guanghui Ren

C

Cheng Ruan

J

Jiaqi Shan

Y

Yongjian Shen

C

Chengshi Shi

M

Mingkang Shi

M

Modi Shi

C

Chonghao Sima

J

Jianheng Song

H

Huijie Wang

W

Wenhao Wang

D

Dafeng Wei

C

Chengen Xie

G

Guo Xu

J

Junchi Yan

C

Cunbiao Yang

L

Lei Yang

S

Shukai Yang

M

Maoqing Yao

J

Jia Zeng

C

Chi Zhang

Q

Qinglin Zhang

B

Bin Zhao

C

Chengyue Zhao

J

Jiaqi Zhao

J

Jianchao Zhu

Format Sitasi

AgiBot-World-Contributors, Bu, Q., Cai, J., Chen, L., Cui, X., Ding, Y. et al. (2025). AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems. https://arxiv.org/abs/2503.06669

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓